摘要
在对 GPL(Generalized Polygonal Line)主曲线算法和指纹数据特点分析的基础上,针对指纹数据本身的特点,改进原来的 GPL 主曲线算法以得到更好的指纹骨架,并实现基于主曲线的指纹特征提取.实验结果表明,改进的 GPL 主曲线算法在指纹骨架提取的效率和效果上比原算法都有明显提高.基于主曲线的指纹特征提取相对于其它一些传统方法也有着更高的准确率,具有一定的应用价值.
Based on the ana principal curve is used sis of GPL principal curve algorithm and the specialties of fingerprint, the to reflect the structure of fingerprint. The original GPL principal curve algorithm is improved to get better skeletonization of fingerprint and the minutiae extraction based on the principal curves is applied. The experimental results show that the improved principal curve algorithm is more efficient and its skeletonization is much better than those of the original ones. The accuracy of minutiae extraction based on the principal curves is also higher than some traditional methods, which has higher value in application.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2007年第6期763-769,共7页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.60175016
60475019)
国家973计划项目(No.2003CB316902)资助
关键词
指纹
细节特征
细节特征提取
主曲线
骨架
Fingerprint, Minutiae, Minutiae Extraction, Principal Curve, Skeletonization
